Learning in Multi-Stage Decentralized Matching Markets
Journal ref Advances in Neural Information Processing Systems (NeurIPS), 2021
作者
Michael I. Jordan
Machine Learning
Learning Strategies in Decentralized Matching Markets under Uncertain Preferences
Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models
Comments 30 pages, 4 figures. The first three authors contributed equally to this work. To appear in AISTATS 2020
Cluster-and-Conquer: A Framework For Time-Series Forecasting
Comments 25 pages, 3 figures
Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametrics
Comments To be more consistent with arxiv policy, and under the advice of the arxiv moderators, we will publish this work as an update to arXiv:1810.06587 rather than its own submission
On the Self-Penalization Phenomenon in Feature Selection
Comments 54 pages
The Stereotyping Problem in Collaboratively Filtered Recommender Systems
A Variational Inequality Approach to Bayesian Regression Games
Comments Accepted by the 60th IEEE Conference on Decision and Control (CDC), Austin, TX, 2021
Distribution-Free, Risk-Controlling Prediction Sets
Comments Project website available at http://www.angelopoulos.ai/blog/posts/rcps/ and codebase available at https://github.com/aangelopoulos/rcps
Stochastic Approximation for Online Tensorial Independent Component Analysis
Comments To appear in Conference on Learning Theory (COLT), 2021
Near-Optimal Algorithms for Minimax Optimization
Comments Accepted by COLT 2020; Improve the writing and fix some confusing parts in the proof
On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms
Comments Derive the explicit dual objective function for APDAMD (Remark 4.2) which satisfies Lemma~4.1; Accepted by ICML 2019; The longer version is available here: arXiv:1906.01437
Data Sharing Markets
On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification
Comments Accepted by AISTATS 2021; Fix some inaccuracy in the definition and proof; 49 Pages, 41 figures
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games
Comments Accepted by ICML 2020; The first two authors contributed equally to this work
Robust Learning of Optimal Auctions
Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
Comments Accepted for the 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021)
Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
Test-time Collective Prediction
Bandit Learning in Decentralized Matching Markets
Comments 34 pages
PAC Best Arm Identification Under a Deadline
Comments In submission
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Comments Accepted to ICML 2021; 31 pages,9 figures
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Comments Accepted to ICML 2021
On dissipative symplectic integration with applications to gradient-based optimization
Comments matches published version
Journal ref J. Stat. Mech. (2021) 043402
Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives
Comments 30 pages; 20 pages appendix and references
Interleaving Computational and Inferential Thinking: Data Science for Undergraduates at Berkeley
The Power of Batching in Multiple Hypothesis Testing
Comments 29 pages, 12 figures
Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization
Comments in Proc. AISTATS'21
Learning from eXtreme Bandit Feedback
Journal ref AAAI Conference on Artificial Intelligence 2021
On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
Comments 76 pages. The short version of this work appears in NeurIPS 2020
